# How to Automate Exploratory Testing with AI > Use AI agents to explore new features, discover untested flows, and generate test cases automatically – exploratory testing at the scale of automation. Source: https://qa.tech/use-cases/exploratory-testing --- Exploratory testing means investigating an application to discover how it behaves and where it breaks, rather than following a fixed script. AI can do this: an agent clicks through a new or changed feature, finds the flows and edge cases, and [proposes test cases](https://docs.qa.tech/best-practices/creating-tests) for what it sees. With QA.tech this runs automatically when a feature lands. [Book a demo](https://qa.tech/demo) Sub-use-cases **Covers** Exploration of a new feature on a PR, discovery of untested areas, auto-generation of candidate cases, edge-case surfacing and automated exploratory testing in agile sprints. 1. 01 ## What exploratory testing uncovers Newly built features with no existing tests, edge cases beyond the happy path, and changed areas where behaviour may have shifted unexpectedly. 2. 02 ## How does an AI agent explore a new feature? When a [PR](https://docs.qa.tech/configuration/github-app) is opened or an area flagged, the agent [crawls](https://docs.qa.tech/core-concepts/crawling) just the changed part of the app, identifies new patterns, and generates concrete cases (e.g., "a dark-mode toggle was added – verify it activates, persists on reload, and is consistent across pages"), which you review and add to a plan. 3. 03 ## When to reach for exploratory testing The moment a new feature lands, before formal cases exist – and whenever you suspect untested risk. 4. 04 ## Who uses automated exploration QA engineers and developers who need new features tested immediately, without designing cases from scratch. 5. 05 ## How QA.tech helps Writing cases for brand-new features is the slowest part of growing coverage. QA.tech does the exploration and proposes the cases, turning a manual bottleneck into a reviewable starting point. ▒ ░▒ ▒ ▓░░ ░▒▓▓░▓░░ ░ ░░ ░░░▒░▒▒░░ ▒░▒░ ░ ░░░░ ░░▓░░▒░ ░░▒█▒ ░ ░▒█ ▓▒ ░░ ▓▒░▒█ ▒ ░░▓ ░░▓░▒ ░░░░░ ░ ░ ░▒▒ ░▒░▓░ ░▒ ▓ ▒▒░░ ▓ ░░░░░░ ▓▓░ ░ ░ ░▓ ░ ▓█ ░▒▒░ ░▒ ▒▒▓ ░ ░░ ░░░░▓ ▒ ▒ ░░▒ ▒▒░ ░▒ ▒▒ ▓░░▓ ░▒▓▓░▒░░█░░▒▒░ ▒░ ▒▓▒ ░░▓ ▓ ▒▒ ░▒▒░░ ░ ▒ ▒░░░░ ## Companies running exploratory testing with QA.tech - [Runs exploratory tests on new features at the pull-request stage.](https://qa.tech/case-studies/how-join-automated-qa-with-ai-agents) FAQ ## Common questions What's the difference between exploratory and scripted testing? Scripted testing re-runs known cases; exploratory discovers unknown behaviour and new cases. QA.tech automates the discovery and hands you cases to keep. Does QA.tech explore the whole app or just changes? For a PR it focuses on the changed area; on demand it can map the whole application. Are the generated tests usable as-is? They come with goals and steps ready to review and promote into a regression plan. Related use cases - [ AI Test Generation Point an agent at a running application and it crawls – reading screens, following links, filling forms – and builds a knowledge graph of the product. From that it proposes test cases as goals in plain language: "a new user can sign up and reach the dashboard." You review the list, keep what matters, delete what doesn't, and edit the ones that are close. What you still decide is which cases matter: an agent can tell you everything the product makes possible, not which of those things would cost you a customer. That judgement stays with you, and it is the part worth your time – it is also the first of the four decisions in our guide to software testing strategies. Read ▒ ░▓▒░ ░░▓▒█░░ █ ░▒▓ ░▓░░ █▒█ ▓░░ ▒ ░░ ░░░ ▒ ▓░▒█ ▓█░░ ░ ░▓░ ░▒ █░░▒░▓▓▓▓ ░▒░░░░░ ░░░▒█ ░▓░▒ ▒░ ▒▓ ░ ░░▓ ░ ▒░░](https://qa.tech/use-cases/ai-test-generation) - [ API Regression Testing You group API contract checks into a plan written as plain-language goals – "GET /orders returns 200 with a list, and every item has an id and a status" – and an AI agent runs them against your API environment on every deploy. The agent makes the requests, writes and executes its own validation code, and returns a verdict with the full request and command trace. Read ░░▓ ░ ▓░▒ ▒ ░▒ ▒▓ ▓ ░░ ▒▓ ░▓░▒░ ▒▓▒░░░░ ▒█ ░ ░ ▓░▒░ ▒ ▓ ▓▓ ░ ░ ░░░ ▓▓▓▒ ░ ░░▓░▓░░█ █░▒░░ ░▓▓░░ ░░▒░░░ ░░ ▓ ░ ▒](https://qa.tech/use-cases/api-regression-testing) - [ Automated Regression Testing Regression testing re-checks that existing features still work after a change. To automate it with AI, you group tests into a regression plan written as plain-language goals, and agents run the whole suite in parallel on every deploy. Many teams wire this into PR testing so the suite runs on every pull request preview. A 50-test suite that took hours by hand finishes in around ten minutes, and the tests don't need rewriting when the UI shifts. This is the workflow behind our automated web testing product. Read ░▒░░░█▒ ░▒ ▒░▓░ ▒░░ ░ █░▒░▒▒ ░░░ ▒█▓░ ▒▓ ▒ ▒ █░ ▒░▓█░█ ░ ▓ ░ ░░▓░ ░ ░░▓ ░▓▓░░ ▓ ░░░▒▒▒░▓ ▓▒ ░░░░░░▒▓░ ▓ ▓ ▓ █](https://qa.tech/use-cases/automated-regression-testing) [← Previous End-to-End Testing ](https://qa.tech/use-cases/end-to-end-testing)[Next → Feature Flag & A/B Test Testing ](https://qa.tech/use-cases/feature-flag-testing) ## Your team moves fast. Can your testing keep up? QA.tech agents test your product autonomously, so moving fast never means shipping broken. See how it works in a 30-minute demo. [Get a demo](https://qa.tech/demo)